使用10x10交叉验证时如何计算ROC？

pythonfrom sklearn.model_selection import StratifiedKFold
from sklearn.metrics import roc_curve, auc
import matplotlib.pyplot as plt

# 假设X是特征矩阵，y是标签向量
# model是已经定义好的分类器

skf = StratifiedKFold(n_splits=10, shuffle=True, random_state=42)
tprs = []
auc_scores = []
mean_fpr = np.linspace(0, 1, 100)

plt.figure(figsize=(10, 8))

for i, (train_index, test_index) in enumerate(skf.split(X, y)):
    X_train, X_test = X[train_index], X[test_index]
    y_train, y_test = y[train_index], y[test_index]
    
    model.fit(X_train, y_train)
    y_pred_prob = model.predict_proba(X_test)[:, 1]
    
    fpr, tpr, thresholds = roc_curve(y_test, y_pred_prob)
    roc_auc = auc(fpr, tpr)
    auc_scores.append(roc_auc)
    
    # 插值得到平均ROC曲线
    tpr_interp = np.interp(mean_fpr, fpr, tpr)
    tpr_interp[0] = 0.0
    tprs.append(tpr_interp)

# 计算平均TPR和标准差
mean_tpr = np.mean(tprs, axis=0)
mean_tpr[-1] = 1.0
mean_auc = auc(mean_fpr, mean_tpr)
std_auc = np.std(auc_scores)

# 绘制平均ROC曲线
plt.plot(mean_fpr, mean_tpr, color='b',
         label=r'Mean ROC (AUC = {0:.2f} $\pm$ {1:.2f})'.format(mean_auc, std_auc),
         lw=2, alpha=.8)

# 绘制对角线
plt.plot([0, 1], [0, 1], linestyle='--', lw=2, color='r',
         label='Chance', alpha=.8)

plt.xlim([-0.05, 1.05])
plt.ylim([-0.05, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver Operating Characteristic (10x10 Cross-Validation)')
plt.legend(loc="lower right")
plt.show()